Improved acoustic modeling for continuous speech recognition
HLT '90 Proceedings of the workshop on Speech and Natural Language
The Lincoln tied-mixture HMM continuous speech recognizer
HLT '90 Proceedings of the workshop on Speech and Natural Language
Hidden Markov Models for Speech Recognition
Hidden Markov Models for Speech Recognition
The SPHINX-II Speech Recognition System: An Overview
The SPHINX-II Speech Recognition System: An Overview
Efficient likelihood evaluation and dynamic Gaussian selection for HMM-based speech recognition
Computer Speech and Language
| Hi-index | 0.00 |
How to capture important acoustic clues and estimate essential parameters reliably is one of the central issues in speech recognition, since we will never have sufficient training data to model various acoustic-phonetic phenomena. Successful examples include subword models with many smoothing techniques. In comparison with subword models, subphonetic modeling may provide a finer level of details. We propose to model subphonetic events with Markov states and treat the state in phonetic hidden Markov models as our basic sub-phonetic unit --- senone. A word model is a concatenation of state-dependent senones and senones can be shared across different word models. Senones not only allow parameter sharing, but also enable pronunciation optimization and new word learning, where the phonetic baseform is replaced by the senonic baseform. In this paper, we report preliminary subphonetic modeling results, which not only significantly reduced the word error rate for speaker-independent continuous speech recognition but also demonstrated a novel application for new word learning.